About Me
I have a total of more than 5 years of experience in the data science field. I have been working hands-on to solve critical business problems for Fortune 500 companies across multiple business sectors using ML, DL and statistics. I have experi...
My expertise lies in understanding/capturing the business problem, converting the business problem into an analytical problem and using the right technology to solve the problem. I am well versed with most of the core technologies and techniques in the data science domain. (Details in the skills/technologies section)
Some of the interesting business problems that I've worked on - Clusterig retail stores, Forecasting weekly sales for stores, Predicting attrition of employees, Predicting failure rate of hardware parts, Analyzing sentiments of tweets about an organisation, Picking relevant information from law book, Extracting text from natural scene images, Extracting entities from news articles etc.
Throughout my career, I have worked in core techniques like clustering, classification, regression, image classification, information retrieval, text classification, object detection etc.
Show MoreSkills
Data & Analytics
Programming Language
Database
Web Development
Others
Development Tools
Positions
Portfolio Projects
Company
Retrieve the most relevant answers from US Tax Law book for questions
Role
Data Scientist
Description
Built an information retrieval model to pick the most relevant answers from the US tax law book for the input
question. Read and implemented the research paper “A Latent Semantic Model with Convolutional-Pooling
structure for Information Retrieval” from scratch in Pytorch.
Company
Extract text from natural scene images
Role
Data Scientist
Company
Predict attrition of employees in a financial year for different service lines
Role
Data Scientist
Description
Built a classification model to predict the attrition probability of each employee for the future financial year based on
historic data. Built an attrition prediction product in dash and deployed it on Azure web app to be used by the clients
Tools
PythonCompany
Generate sentiment score for an organization based on live tweets
Role
Data Scientist
Description
Built a sentiment analysis model to analyze the live tweets about the organization. Converted the predicted
sentiments into a quantifiable score. Led a team of 4 through the entire lifecycle of the project along with handling
client conversations.
Tools
PythonCompany
Cluster retail stores with similar sales pattern and forecast weekly sales for the stores
Role
Data Scientist
Description
Performed time series clustering analysis to group stores based on their sales pattern and used these clusters to
forecast weekly sales for the stores, thus reducing the complexity involved in the store-level forecast process.
Skills
Rstudio K-means Clustering SQLTools
rstudio